Imitation Learning of Agenda-based Semantic Parsers

Jonathan Berant, Percy Liang


Abstract
Semantic parsers conventionally construct logical forms bottom-up in a fixed order, resulting in the generation of many extraneous partial logical forms. In this paper, we combine ideas from imitation learning and agenda-based parsing to train a semantic parser that searches partial logical forms in a more strategic order. Empirically, our parser reduces the number of constructed partial logical forms by an order of magnitude, and obtains a 6x-9x speedup over fixed-order parsing, while maintaining comparable accuracy.
Anthology ID:
Q15-1039
Volume:
Transactions of the Association for Computational Linguistics, Volume 3
Month:
Year:
2015
Address:
Cambridge, MA
Editors:
Michael Collins, Lillian Lee
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
545–558
Language:
URL:
https://aclanthology.org/Q15-1039
DOI:
10.1162/tacl_a_00157
Bibkey:
Cite (ACL):
Jonathan Berant and Percy Liang. 2015. Imitation Learning of Agenda-based Semantic Parsers. Transactions of the Association for Computational Linguistics, 3:545–558.
Cite (Informal):
Imitation Learning of Agenda-based Semantic Parsers (Berant & Liang, TACL 2015)
Copy Citation:
PDF:
https://aclanthology.org/Q15-1039.pdf
Code
 worksheets/0x8fdfad31